{"id":"https://openalex.org/W4401608884","doi":"https://doi.org/10.1109/icasspw62465.2024.10626759","title":"Music Enhancement with Deep Filters: A Technical Report for the ICASSP 2024 Cadenza Challenge","display_name":"Music Enhancement with Deep Filters: A Technical Report for the ICASSP 2024 Cadenza Challenge","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401608884","doi":"https://doi.org/10.1109/icasspw62465.2024.10626759"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04766542v1/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113182213","display_name":"Keren Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keren Shao","raw_affiliation_strings":["University of California,San Diego,USA","UC San Diego - University of California [San Diego] (UCSD, 9500 Gilman Dr., La Jolla, CA 92093 USA - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,San Diego,USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"UC San Diego - University of California [San Diego] (UCSD, 9500 Gilman Dr., La Jolla, CA 92093 USA - United States)","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451980","display_name":"Ke Chen","orcid":"https://orcid.org/0000-0001-8357-3741"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["University of California,San Diego,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,San Diego,USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042278809","display_name":"Shlomo Dubnov","orcid":"https://orcid.org/0000-0003-0222-1125"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shlomo Dubnov","raw_affiliation_strings":["University of California,San Diego,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,San Diego,USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4325546622276306},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42939454317092896},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.23437431454658508}],"concepts":[{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4325546622276306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42939454317092896},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.23437431454658508}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10626759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04766542v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04766542/document","pdf_url":"https://hal.science/hal-04766542v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), Apr 2024, Seoul, France. pp.119-120, ⟨10.1109/ICASSPW62465.2024.10626759⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04766542v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04766542/document","pdf_url":"https://hal.science/hal-04766542v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), Apr 2024, Seoul, France. pp.119-120, ⟨10.1109/ICASSPW62465.2024.10626759⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401608884.pdf","grobid_xml":"https://content.openalex.org/works/W4401608884.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2240897131","https://openalex.org/W3001377302","https://openalex.org/W3149794337","https://openalex.org/W3160085755","https://openalex.org/W3205770165","https://openalex.org/W3213726885","https://openalex.org/W4226300471","https://openalex.org/W4385822305","https://openalex.org/W4385822734","https://openalex.org/W6746914816","https://openalex.org/W6773772901"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"this":[1],"challenge,":[2],"we":[3],"disentangle":[4],"the":[5,9,32,35,56,61,71],"deep":[6,36],"filters":[7],"from":[8],"original":[10],"DeepfilterNet":[11],"and":[12,60],"incorporate":[13],"them":[14],"into":[15],"our":[16,79],"Spec-UNet-based":[17],"network":[18],"to":[19],"further":[20],"improve":[21],"a":[22],"hybrid":[23],"Demucs":[24],"(hdemucs)":[25],"based":[26],"remixing":[27],"pipeline.":[28],"The":[29],"motivation":[30],"behind":[31],"use":[33],"of":[34,73,78],"filter":[37],"component":[38],"lies":[39],"at":[40],"its":[41],"potential":[42],"in":[43,54],"better":[44],"handling":[45],"temporal":[46],"fine":[47],"structures.":[48],"We":[49],"demonstrate":[50],"an":[51],"incremental":[52],"improvement":[53],"both":[55],"Signal-to-Distortion":[57],"Ratio":[58],"(SDR)":[59],"Hearing":[62],"Aid":[63],"Audio":[64],"Quality":[65],"Index":[66],"(HAAQI)":[67],"metrics":[68],"when":[69],"comparing":[70],"performance":[72],"hdemucs":[74],"against":[75],"different":[76],"versions":[77],"model.":[80]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}